# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# ===========================================================
# robots.txt — Tribuna Dominicana
# https://www.tribunadominicana.net/robots.txt
# Última actualización: junio 2025
# ===========================================================

# ---- Todos los robots (reglas generales) ----
User-agent: *

# Permitir todo el sitio de forma predeterminada
Allow: /

# Bloquear páginas de administración y archivos internos
Disallow: /admin/
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /cgi-bin/
Disallow: /private/
Disallow: /tmp/
Disallow: /cache/
Disallow: /logs/
Disallow: /includes/
Disallow: /config/
Disallow: /backup/
Disallow: /.env
Disallow: /package.json
Disallow: /composer.json

# Bloquear URLs de búsqueda interna con parámetros (evitar contenido duplicado)
Disallow: /*?s=
Disallow: /*?search=
Disallow: /*?q=
Disallow: /*?query=
Disallow: /*?p=
Disallow: /*?page=
Disallow: /*?replytocom=
Disallow: /*?preview=true
Disallow: /*&preview=true

# Bloquear URLs de impresión
Disallow: /*/print/
Disallow: /*?print=

# Bloquear URLs de feeds (opcionales, actívelos si los usa)
# Disallow: /feed/
# Disallow: /*/feed/

# ---- Googlebot (acceso completo al CSS y JS) ----
User-agent: Googlebot
Allow: /assets/css/
Allow: /assets/js/
Allow: /assets/images/
Allow: /

# ---- Bingbot ----
User-agent: Bingbot
Allow: /assets/css/
Allow: /assets/js/
Allow: /assets/images/
Allow: /

# ---- Google Image Bot ----
User-agent: Googlebot-Image
Allow: /assets/images/
Allow: /

# ---- Google News Bot (para indexación en Google News) ----
User-agent: Googlebot-News
Allow: /noticias/
Allow: /internacional/
Allow: /opinion/
Allow: /entretenimiento/
Allow: /sociedad/
Allow: /turismo/
Allow: /educacion/

# ---- Bloquear bots de scraping y rastreo masivo ----
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SeznamBot
Crawl-delay: 10

# ---- Delay de rastreo para bots secundarios ----
User-agent: *
Crawl-delay: 2

# ---- Ubicación del Sitemap XML ----
Sitemap: https://www.tribunadominicana.net/sitemap.xml

# ---- Host canónico ----
Host: https://www.tribunadominicana.net